Please use this identifier to cite or link to this item:
Title: Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
Authors: Ng, Wan Ling.
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2012
Abstract: Singing Voice Synthesis has been researched on and developed extensively for 50 years and beyond. Till date, many research studies have been to produce operatic singing voices, using practical approaches such as Vocal Tract Length Normalisation (VTLN) and other methods of synthesis. Singing Voice Synthesis involves the controlling of the three acoustic features unique to singing voices, namely the fundamental frequency (F0), phoneme duration, and spectrum. Through extracting these features into which of a set of classes, it helps to develop the diversity and functionality of the application.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
12.26 MBAdobe PDFView/Open

Page view(s)

checked on Oct 1, 2020


checked on Oct 1, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.